US Patent Issued to GOOGLE on May 26 for "Utilizing large language model (LLM) in responding to multifaceted queries" (American, Israeli Inventors)

ALEXANDRIA, Va., May 26 -- United States Patent no. 12,639,300, issued on May 26, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Utilizing large language model (LLM) in responding to multifaceted queries" was invented by Asaf Revach (Nordia Center District, Israel), Hongrae Lee (Mountain View, Calif.) and Zhengzhong Liang (Melrose, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Implementations leverage a generative model (e.g., a large language model (LLM)) to generate a plurality of candidate subqueries for multifaceted natural language (NL) based input, where each of the candidate subqueries is potentially directed to a facet or problem of the multifaceted NL based input. Those implementations ...